© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104288
    Prev
    Next
    INDEX
    Explanations

    recent and past times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    谙
    -0.86
     dejen
    -0.85
    ांकि
    -0.82
    王的
    -0.82
     tüm
    -0.82
     entonces
    -0.80
    enaire
    -0.80
     होगा
    -0.80
     oude
    -0.79
    〙
    -0.79
    POSITIVE LOGITS
     recently
    2.70
     yesterday
    2.47
     today
    2.31
     tonight
    2.11
     last
    2.03
    Recently
    1.84
    recently
    1.83
     recent
    1.79
     lately
    1.79
     latest
    1.73
    Activations Density 0.184%

    No Known Activations